pycaption 2.3.2__tar.gz → 2.3.3__tar.gz

{pycaption-2.3.2/pycaption.egg-info → pycaption-2.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycaption
-Version: 2.3.2
+Version: 2.3.3
 Summary: Closed caption converter
 Author: Joe Norton
 Author-email: joey@nortoncrew.com

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/base.py

@@ -64,6 +64,33 @@ class BaseReader:
     def __init__(self, *args, **kwargs):
         pass
 
+    @staticmethod
+    def _decode_content(content):
+        """Decode bytes to str (UTF-8 with BOM handling).
+
+        :param content: str or bytes input.
+        :returns: decoded str with BOM stripped.
+        :raises InvalidInputError: if content is not str/bytes, is empty
+            bytes, or is not valid UTF-8.
+        """
+        if isinstance(content, bytes):
+            if not content:
+                raise InvalidInputError("The content is empty.")
+            try:
+                content = content.decode("utf-8-sig")
+            except UnicodeDecodeError as e:
+                raise InvalidInputError(
+                    f"Content is not valid UTF-8: {e}"
+                ) from e
+        elif isinstance(content, str):
+            if content.startswith(""):
+                content = content[1:]
+        else:
+            raise InvalidInputError(
+                "The content must be a unicode string or UTF-8 bytes."
+            )
+        return content
+
     def detect(self, content):
         """Return True if content appears to be in this reader's format.
 

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/dfxp/reader.py

@@ -21,7 +21,6 @@ from ..exceptions import (
     CaptionReadNoCaptions,
     CaptionReadSyntaxError,
     CaptionReadTimingError,
-    InvalidInputError,
 )
 from ..geometry import (
     Alignment,
@@ -108,9 +107,10 @@ class DFXPReader(BaseReader):
     def detect(self, content):
         """Return True if content looks like a DFXP/TTML document.
 
-        :type content: str
+        :type content: str or bytes
         :rtype: bool
         """
+        content = self._decode_content(content)
         lowered = content.lower()
         return bool(re.search(r"<tt[\s>]", lowered)) and "</tt>" in lowered
 
@@ -122,8 +122,7 @@ class DFXPReader(BaseReader):
         :raises InvalidInputError: if content is not a string
         :raises CaptionReadNoCaptions: if no captions are found
         """
-        if not isinstance(content, str):
-            raise InvalidInputError("The content is not a unicode string.")
+        content = self._decode_content(content)
 
         dfxp_document = LayoutAwareDFXPParser(
             content, read_invalid_positioning=self.read_invalid_positioning

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/microdvd.py

@@ -20,7 +20,6 @@ from .exceptions import (
     CaptionReadNoCaptions,
     CaptionReadSyntaxError,
     CaptionReadTimingError,
-    InvalidInputError,
 )
 from .geometry import HorizontalAlignmentEnum
 
@@ -30,6 +29,7 @@ class MicroDVDReader(BaseReader):
 
     def detect(self, content):
         """Return True if content starts with MicroDVD frame markers."""
+        content = self._decode_content(content)
         return re.match(r"{\d+}{\d+}", content) is not None
 
     def read(self, content, lang=DEFAULT_LANGUAGE_CODE):
@@ -39,8 +39,7 @@ class MicroDVDReader(BaseReader):
         :param lang: Language code to assign.
         :rtype: CaptionSet
         """
-        if not isinstance(content, str):
-            raise InvalidInputError("The content is not a unicode string.")
+        content = self._decode_content(content)
 
         lines = content.splitlines()
         captions = CaptionList()

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/sami/reader.py

@@ -10,7 +10,6 @@ from ..base import BaseReader, Caption, CaptionList, CaptionNode, CaptionSet
 from ..exceptions import (
     CaptionReadNoCaptions,
     CaptionReadTimingError,
-    InvalidInputError,
 )
 from ..geometry import Alignment, HorizontalAlignmentEnum, Layout, Padding, Size
 from .parser import SAMIParser
@@ -32,6 +31,7 @@ class SAMIReader(BaseReader):
 
     def detect(self, content):
         """Return True if content looks like a SAMI document."""
+        content = self._decode_content(content)
         return "<sami" in content.lower()
 
     def read(self, content):
@@ -42,8 +42,7 @@ class SAMIReader(BaseReader):
         :raises InvalidInputError: if content is not a string
         :raises CaptionReadNoCaptions: if no captions are found
         """
-        if not isinstance(content, str):
-            raise InvalidInputError("The content is not a unicode string.")
+        content = self._decode_content(content)
 
         content, doc_styles, doc_langs = SAMIParser().feed(content)
         sami_soup = BeautifulSoup(content, features="lxml")

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/scc/reader.py

@@ -87,7 +87,6 @@ from pycaption.exceptions import (
     CaptionLineLengthError,
     CaptionReadNoCaptions,
     CaptionReadTimingError,
-    InvalidInputError,
 )
 
 from .constants import (
@@ -148,10 +147,11 @@ class SCCReader(BaseReader):
     def detect(self, content):
         """Checks whether the given content is a proper SCC file
 
-        :type content: str
+        :type content: str or bytes
 
         :rtype: bool
         """
+        content = self._decode_content(content)
         lines = content.splitlines()
         if lines[0] == HEADER:
             return True
@@ -177,8 +177,7 @@ class SCCReader(BaseReader):
 
         :rtype: CaptionSet
         """
-        if not isinstance(content, str):
-            raise InvalidInputError("The content is not a unicode string.")
+        content = self._decode_content(content)
 
         self.simulate_roll_up = simulate_roll_up
         self.time_translator.offset = offset * 1000000

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/srt.py

@@ -6,7 +6,7 @@ from .base import (
     BaseReader, BaseWriter, Caption, CaptionList, CaptionNode, CaptionSet,
     merge_caption_list,
 )
-from .exceptions import CaptionReadNoCaptions, InvalidInputError
+from .exceptions import CaptionReadNoCaptions
 from .geometry import HorizontalAlignmentEnum
 
 
@@ -19,6 +19,7 @@ class SRTReader(BaseReader):
         Checks that the first line is a sequence number and the second
         contains an arrow ('-->').
         """
+        content = self._decode_content(content)
         lines = content.splitlines()
         if lines[0].isdigit() and "-->" in lines[1]:
             return True
@@ -34,8 +35,7 @@ class SRTReader(BaseReader):
         :raises InvalidInputError: if content is not a string.
         :raises CaptionReadNoCaptions: if no captions are found.
         """
-        if not isinstance(content, str):
-            raise InvalidInputError("The content is not a unicode string.")
+        content = self._decode_content(content)
 
         lines = content.splitlines()
         start_line = 0

{pycaption-2.3.2 → pycaption-2.3.3}/pycaption/webvtt/reader.py

@@ -15,7 +15,6 @@ from ..exceptions import (
     CaptionReadNoCaptions,
     CaptionReadSyntaxError,
     CaptionReadWarning,
-    InvalidInputError,
 )
 from ..geometry import (
     Alignment,
@@ -126,8 +125,7 @@ class WebVTTReader(BaseReader):
         optionally followed by a space or tab and header metadata.
         Handles BOM-prefixed content.
         """
-        if content.startswith(""):
-            content = content[1:]
+        content = self._decode_content(content)
         first_line = content.splitlines()[0] if content.strip() else ""
         return (
             first_line == "WEBVTT"
@@ -147,20 +145,7 @@ class WebVTTReader(BaseReader):
         :raises InvalidInputError: If content is not a string.
         :raises CaptionReadNoCaptions: If no cues are found.
         """
-        if isinstance(content, bytes):
-            if not content:
-                raise InvalidInputError("The content is not a unicode string.")
-            try:
-                content = content.decode("utf-8")
-            except UnicodeDecodeError as e:
-                raise InvalidInputError(
-                    f"WebVTT content is not valid UTF-8: {e}"
-                ) from e
-        elif not isinstance(content, str):
-            raise InvalidInputError("The content is not a unicode string.")
-
-        if content.startswith(""):
-            content = content[1:]
+        content = self._decode_content(content)
 
         # str.splitlines() handles CR, LF, CRLF (W3C WebVTT §3 RULE-FMT-005)
         lines = content.splitlines()

{pycaption-2.3.2 → pycaption-2.3.3/pycaption.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycaption
-Version: 2.3.2
+Version: 2.3.3
 Summary: Closed caption converter
 Author: Joe Norton
 Author-email: joey@nortoncrew.com

{pycaption-2.3.2 → pycaption-2.3.3}/setup.py

@@ -20,7 +20,7 @@ transcript_dependencies = ["nltk==3.10.0"]
 
 setup(
     name="pycaption",
-    version="2.3.2",
+    version="2.3.3",
     description="Closed caption converter",
     long_description=open(README_PATH).read(),
     author="Joe Norton",

{pycaption-2.3.2 → pycaption-2.3.3}/tests/mixins.py

@@ -17,10 +17,20 @@ class ReaderTestingMixIn:
     def assert_negative_answer_for_detection(self, different_sample):
         assert self.reader.detect(different_sample) is False
 
-    def test_reader_only_supports_unicode_input(self):
+    def test_reader_rejects_non_string_non_bytes_input(self):
+        with pytest.raises(InvalidInputError) as exc_info:
+            self.reader.read(123)
+        assert "must be a unicode string or UTF-8 bytes" in exc_info.value.args[0]
+
+    def test_reader_rejects_empty_bytes(self):
         with pytest.raises(InvalidInputError) as exc_info:
             self.reader.read(b"")
-        assert exc_info.value.args[0] == "The content is not a unicode string."
+        assert exc_info.value.args[0] == "The content is empty."
+
+    def test_reader_rejects_invalid_utf8_bytes(self):
+        with pytest.raises(InvalidInputError) as exc_info:
+            self.reader.read(b"\xff\xfe invalid utf8")
+        assert "not valid UTF-8" in exc_info.value.args[0]
 
 
 class WebVTTTestingMixIn: